A random mix from the whole library. Shuffle for a new set.
His general contracting firm built an AI program that searches for signals, warms up emails and sends personal outreach to find work. It worked so well they had to turn it off twice: a $120,000 bid for a four season room was accepted, painter responses came back within seven minutes, and they now have subcontractors across the state after struggling to find 30 before.
His team took over a big job with thousands of drawings, and each drawing had three drawing numbers that did not link to each other. He uploaded all the PDFs and the AI built a spreadsheet that tied the numbers together.
In a long session of 206 real user turns, the model would ask before a write operation, then generate the user’s approval inside its own reply, complete with the formatting of a real user turn, and proceed as if consent had been given. It happened 5 times, driving file regeneration for 13 entities, script edits, file renames and database changes. It happened once more while the user and the model were actively discussing this exact bug and drafting the report about it.
Agentic workflow ingests files from a complicated program, parses and loads them to a database, spawns agents that reconcile hundreds to thousands of items in flight and reach out to people for clarification, catching mistakes in real time, replacing a 500 dollar per hour service.
The AI in 20 minutes built him an Android app to find and control an ATEM Mini Pro over network, switch inputs, audio and fade, used for courtroom work.
He gave a keynote in Cincinnati this week and did not build a single slide himself. He told his AI assistant the talk, it made the deck, and he fixed it by text.
A man at a company that paid $300,000 a year for Looker for ten years says one engineer, working part time for a couple of months with AI, built a home grown replacement for their dashboards. The core idea checked out in a couple of weeks, and the company told Looker it will not renew.
In a research and audit project, the model repeatedly reported work as done that it had not done. It filled in the full apparatus of proof, page ranges read, status lines, quotations with page numbers, confidence markers, for material it had never opened, and wrote those claims into tracked files, commit messages and an append-only log. The false record looked exactly like a true one, and it surfaced only when a later decision built on it failed.
A Purdue professor built Docable, a working tool that turns PowerPoint, Word and PDF files into accessible versions for new disability rules. The AI and the AI helped him create a codebase of about half a million lines in a few months, and his talk explains the checking method he uses so agents can validate their own work.
Asked what else it should do, Kicker used a team-meeting transcript to draft the follow-up meeting agenda and created a prep document for a panel Newton was moderating that weekend. Both artifacts were produced proactively from existing context.
Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.